figma-use-motion

作者: openai

Motion / animation context for the `use_figma` MCP tool — animating Figma nodes via manual keyframes, animation styles, easing, and timeline duration. Load…

npx skills add https://github.com/openai/plugins --skill figma-use-motion

use_figma — Figma Plugin API Skill for Motion

Motion context for the use_figma MCP tool. figma-use covers the foundational Plugin API rules — load both together.

Always pass skillNames: "figma-use-motion" (comma-separated alongside figma-use) when calling use_figma for motion work. Logging only.

Runtime Gating

Motion APIs are gated behind the metronome user feature flag. When the calling user doesn't have it, every motion property and helper referenced in this skill throws "<name>" is not a supported API.

Bail out fast on that error. Do not retry; tell the user motion isn't enabled for them and stop. Otherwise you'll burn calls and confuse the user with repeated identical failures.

When to use this skill

Load this skill whenever a use_figma task involves:

  • Adding, editing, or removing keyframes on a node (manualKeyframeTracks, applyManualKeyframeTrack, removeManualKeyframeTrack).
  • Animating fill or stroke colors over time.
  • Applying, editing, or removing animation styles (applyAnimationStyle, removeAnimationStyle, animationStyles).
  • Reading or writing timeline duration via node.timelines / node.setTimelineDuration(id, seconds).
  • Choosing easing for any of the above.

Static design work (creating shapes, components, variables, layout) goes through figma-use alone — this skill is only for the time dimension.

Exposed motion API surface

  • node.manualKeyframeTracks — read/write manual keyframes (including fill, stroke, and effect tracks).
  • node.applyManualKeyframeTrack(field, track) / node.removeManualKeyframeTrack(field) — add, replace, or remove one manual keyframe track without rewriting the whole object.
  • node.animationStyles — read/write animation-style metadata applied to a node.
  • node.applyAnimationStyle(styleId, presetData?) / node.removeAnimationStyle(id) — apply a discovered style and remove an applied style instance by its returned/read-back id.
  • node.timelines — read-only timeline list for the containing top-level frame, with durations in seconds.
  • node.setTimelineDuration(id, durationSeconds) — write the containing top-level frame timeline duration.
  • node.animations — read-only resolved keyframe data (currently manual tracks only — see motion-patterns.md).
  • figma.motion.figmaAnimationStyles() — read-only list of Figma's first-party animation styles.

Authoring custom "figma:motion" preset module source code is out of scope. If the user wants a brand-new animation style, say so and stop; don't fabricate one.

Reference docs

Load these as needed based on what the task involves:

DocWhen to loadWhat it covers
motion-patterns.mdAdding/editing motion animationManual keyframes, animated fills/strokes, applying animation styles, timeline duration
motion-easing.mdSetting animation easingKeyframe easing objects, custom cubic/spring, HOLD, applying easing inside an animation style

Verifying the animation

get_screenshot shows only the timeline's resting state, never motion. To check motion, export_video and sample frames — but it renders server-side and is slow and expensive (~10s to minutes), so make each render count.

Plan before rendering — cost scales with pixels × frames, so keep both no larger than the frames need:

  1. Pick the moments first. You need one frame per phase (e.g. per stagger step, or start / mid / settle), not smooth playback — usually 4–6. This count sets your fps.
  2. Size to what you must read. Start small — constraint: { type: 'WIDTH', value: 320 }, quality: "low" — but text and small elements blur there, so raise WIDTH (768+) when you need to judge fine detail. Omitting constraint = full size (1x; server clamps to 10x / 4096px).
  3. Set fps just high enough to land those frames: fps: 5 covers a handful; 10 is an upper bound. Higher just bloats the render.

Mechanics: export_video works only on a top-level frame whose children carry the animation (pass that frame, not the descendant you keyframed). It returns a jobId with status: "processing" — re-invoke with { fileKey, jobId } to poll. Then extract frames locally with ffmpeg -ss <t> -i anim.mp4 -frames:v 1 frame_<t>.png — extraction is free, so once you've paid for the render, mine it for every frame that tells you something rather than re-exporting. Without a frame extractor like ffmpeg, skip the export and reason about the keyframes instead.

Iterate until it's right. The export is a diagnostic, not a sign-off: if the frames are wrong (bad order, off timing, a missing element, a mask blanking the composite), fix the keyframes/styles and re-export. Read all the frames and batch every fix into one pass before re-rendering — every render carries real overhead, so make each one count instead of re-exporting after each small change.

Skip the export entirely for trivial or self-evident changes.

Pre-flight checklist

In addition to the figma-use pre-flight checklist, verify:

  • Easing uses the public { type: 'EASE_OUT', easingFunctionCubicBezier?: …, easingFunctionSpring?: … } shape — not internal scenegraph names like OUT_CUBIC.
  • Ease-in-out uses the exact public enum EASE_IN_AND_OUT (or EASE_IN_AND_OUT_BACK); never emit the invalid alias EASE_IN_OUT.
  • The node being animated is not a top-level frame (direct child of a page). Animate descendants instead.
  • Timeline values are seconds in the public Plugin API. Extend via setTimelineDuration; never shorten unless the user asked.
  • Transform keyframe fields use public names (TRANSLATION_X, TRANSLATION_Y, ROTATION, SCALE_X, SCALE_Y, SCALE_XY), not internal MOTION_* scenegraph names.
  • Manual keyframe fields come from the public allowlist in motion-patterns.md; generated/internal scenegraph fields intentionally throw.
  • Mutated node IDs are returned (per figma-use Rule 15).
  • When motion correctness isn't self-evident and a frame extractor (ffmpeg) is available, verify via export_video + frame sampling — render small, low fps, iterate until right (see the Verifying the animation section above). get_screenshot shows only the resting state.

來自 openai 的更多技能

user-context
openai
載入或管理資料分析插件的持久性來源路由偏好設定、入門邏輯、設定進度以及語義層註冊表。
official
notion-research-documentation
openai
研究Notion內容,並將其整合為結構化的簡報、報告或附有引用的比較分析。透過精準查詢搜尋並擷取Notion頁面,然後按主題組織發現,並附上內文來源引用及參考文獻章節。根據範圍與使用者目標,從四種輸出格式(快速簡報、研究摘要、比較分析、綜合報告)中選擇。使用內建範本建立與更新Notion頁面;直接連結來源,並在新資訊到來時追蹤變更。
official
rcsb-pdb-skill
openai
提交精簡的RCSB PDB請求以獲取核心元數據、Search API查詢及FASTA下載。當用戶需要簡潔的RCSB摘要時使用;保存原始JSON或…
official
pdf
openai
PDF 讀取、建立與驗證,支援視覺化渲染與程式化生成。使用 Poppler(pdftoppm)將 PDF 頁面渲染為 PNG,以便在交付前檢查版面、間距與排版。透過 reportlab 程式化生成 PDF,確保格式可靠;使用 pdfplumber 或 pypdf 提取文字與元資料。執行品質標準:無文字裁切、元素重疊、表格破損或渲染瑕疵;僅使用 ASCII 連字號,引用格式需具可讀性。使用...
official
test-coverage-improver
openai
Improve test coverage in the OpenAI Agents JS monorepo: run `pnpm test:coverage`, inspect coverage artifacts, identify low-coverage files and branches, propose…
official
playwright
openai
終端驅動的瀏覽器自動化,具備元素快照與互動式UI工作流程。透過playwright-cli包裝腳本運作(需npx),支援無頭模式與有頭模式以進行視覺化除錯。核心流程:開啟頁面、擷取快照以取得穩定元素參照、使用參照進行互動、在導航或DOM變更後重新擷取快照。包含表單填寫、點擊、輸入、多分頁管理、螢幕截圖/PDF擷取,以及流程除錯的軌跡記錄。元素參照(例如e3、e15)...
official
ukb-topmed-phewas-skill
openai
接受rsID、GRCh37或GRCh38輸入,解析為所需的GRCh38查詢,以獲取單一變異的簡潔UKB-TOPMed PheWAS摘要。當需要…時使用。
official
code-review-context
openai
模型可見上下文
official